• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1997년도 춘계학술대회
• /
• pp.478-483
• /
• 1997

The SNUH has started a PACS project with three main goals : to develop a fully hospital-integrated PACS, to develop a cost effective PACS using open systems architecture, and to extend PACS' role to the advanced application such as image guided surgery, multi-media assisted education and research. In order to achieve these goals, we have designed a PACS architecture which takes advantages of client-server computing, high speed communication network, computing power of up-to-date high-end PC, and advanced image compression method. We have installed ATM based communication network in radiology department and in-patient wards, and implemented DICOM compliant acquisition modules, image storage and management servers, and high resolution display workstations based on high-end PC and Microsoft Windows 95 and Windows NT operating systems. The SNUH PACS is in partial scale operation now, and will be expanded to full scale by the end of 1998.

• 한국컴퓨터정보학회논문지
• /
• 제3권2호
• /
• pp.139-146
• /
• 1998

비촛점흐려짐과 가산잡음에 의해 훼손된 영상을 정칙화 공액경사법을 이용하여 복원하는 방법을 제안하였다. 기존의 반복복원방법에 비하여 공액경사법은 초선형적인 수렴속도로 해에 수렴할 뿐 아니라 한정된 반복 횟수 내에 원래의 해에 수렴할 수 있다는 장점을지닌다. 본 논문은 반복복원시 잡음의 증폭을 억제하기 위하여 정칙화 공액 경사법에 구속조건을 적용함으로써 적응적으로 윤곽부분과 평면부분의 복원을 행하는 정칙화 공액경사법을 제안하였다. 제안한 방법은 기존의 방법에 비해, 윤곽부분에서는 1에 근사한 구속조건의값을 적용함으로서 윤곽의 복원을 행하고, 평면부분에서는 0에 근사하는 구속조건을 정칙화 공액경사법에 적용함으로써 잡음을 증폭을 억제할 수 있다는 장점을 지닌다.

• 한국멀티미디어학회논문지
• /
• 제20권2호
• /
• pp.101-107
• /
• 2017

LabVIEW coding for video dehazing was developed. The dark channel prior proposed by K. He was applied to remove fog based on a single image, and K. B. Gibson's median dark channel prior was applied, and implemented in LabVIEW. In other words, we improved the image processing speed by converting the existing fog removal algorithm, dark channel prior, to the LabVIEW system. As a result, we have developed a real-time fog removal system that can be commercialized. Although the existing algorithm has been utilized, since the performance has been verified real - time, it will be highly applicable in academic and industrial fields. In addition, fog removal is performed not only in the entire image but also in the selected area of the partial region. As an application example, we have developed a system that acquires clear video from the long distance by connecting a laptop equipped with LabVIEW SW that was developed in this paper to a 100~300 times zoom telescope.

• 방송공학회논문지
• /
• 제16권3호
• /
• pp.427-438
• /
• 2011

논문에서는 디스플레이 촬영 영상을 기반으로 하는 콘텐츠 검색 방법을 제안한다. 본 논문에서 제안한 알고리즘은 조명 등의 촬영 조건 변화에 영향을 최소화하기 위해 인접 블록 간 휘도의 증감 방향을 표현하는 이진 맵을 이용한다. 또한 본 논문에서 구현한 콘텐츠 검색 시스템은 제안 알고리즘의 효율성을 높이기 위해 스칼라 값을 이용한 인덱스 기반의 2단계 검색을 수행한다. 알고리즘 비교 실험을 통해 제안 알고리즘에 대한 검증을 수행하고 제안 알고리즘을 이용하여 구현한 콘텐츠 검색 시스템을 기술한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 추계학술발표대회
• /
• pp.781-784
• /
• 2017

얼굴인식 시스템은 비접촉데이터 채집의 특성과 함께, 그 정확도가 점차 향상되고 있다. 공공 감시카메라와 같이 사진을 멀리서 찍는 상황에서는 저해상도의 얼굴 이미지로 인해 얼굴인식 시스템을 효과적으로 사용할 수 없는 경우가 있다. 이론적으로는 저해상도영상을 Super Resolution (SR) 방법으로 고해상도 영상으로 바꾸어 얼굴인식에 사용할 수 있지만, 기존의 SR 방법들은 얼굴 인식에 만족할만한 결과를 내지 못할 수 있다. 이 논문은 극 저해상도 (very low resolution) 얼굴인식 문제를 살펴보고 편미분방정식 기반 SR 방법을 제안하고, CNN 기반 얼굴인식 시스템에 응용한다.

• 한국지능시스템학회논문지
• /
• 제18권1호
• /
• pp.48-52
• /
• 2008

본 논문은 가려진 얼굴 영상을 효과적으로 인식하기 위한 선택적 부공간 투영 방법을 제안하였다. 기존의 부공간 투영방법은 가려짐이 있는 얼굴의 전체 영상을 기저 영상에 투영하였다. 얼굴의 특징 부분은 가려짐에 의해 왜곡되기 쉽기 때문에 얼굴 인식률의 저하가 크게 발생한다. 이를 극복하기 위해 제안 방법은 먼저 가려짐의 유무를 판단하고 가려짐이 없는 경우는 기존의 부공간 투영 방법으로 전체적인 기저 벡터에 투영하여 특징 벡터를 구하였고, 가려짐이 있는 경우는 가려짐이 존재하는 영역을 배제된 부분적인 기저 벡터에 투영하여 특징 벡터를 구하였다. 가려짐이 있는 얼굴 영상을 제공하는 AR 얼굴 데이터베이스를 이용하여 실험한 결과, 기존의 PCA 및 NMF 보다 좋은 인식률을 보였다.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2003년도 춘계학술대회 논문집
• /
• pp.109-114
• /
• 2003

Wireless communication systems are inevitable for efficient underwater activities. Because of the poor propagation characteristics of light and electromagnetic waves, acoustic waves are generally used for the underwater wireless communication. Although there are many kinds of information type, visual images take an essential role especially for search and identification activities. For this reason, we developed an acoustic-based underwater image transmission system under a dual use technology project supported by MOCIE (Ministry of Commerce, Industry and Energy). For the application to complicated and time-varying underwater environments all-digital transmitter and receiver systems are investigated. Array acoustic transducers are used at the receiver, which have the center frequency of 32kHz and the bandwidth of 4kHz. To improve transmission speed and quality, various algorithms and systems are used. The system design techniques will be discussed in detail including image compression/ decompression system, adaptive beam- forming, fast RLS adaptive equalizer, ${\partial}/4$ QPSK (Quadrilateral Phase Shift Keying) modulator/demodulator, and convolution coding/ Viterbi. Decoding.

• 조명전기설비학회논문지
• /
• 제29권5호
• /
• pp.1-12
• /
• 2015

In this study, we derive an evaluation structure and 18 Valuation vocabulary for the media facade lighting conditions. In addition, this study deduced the applicable elements that could be applied in time of building nightscape lighting design using media facade by conducting affective evaluation. The research results are as follows: It was found that the image axis of "Dynamic, Colorful" showed the lighting change speed was fast with diverse application of lighting color, and its evaluation object applied by general emphasis, vertical emphasis, partial emphasis lighting method was highly assessed. In addition, it was found that "Luxurious, Unusual" axis showed lighting change speed was slow with the application of lighting color in warm hue series, and its evaluation object applied by line lighting, dot lighting, general emphasis lighting methods was highly assessed. Lastly, it was found that "Soft, Secure" image axis showed the lighting change speed was slow with the application of pastel tone lighting color, and the evaluation object applied by general emphasis lighting method was highly assessed.

• 패션비즈니스
• /
• 제23권5호
• /
• pp.19-30
• /
• 2019

The aim of this study is to analyze the stage of image change in Korean fashion design in regards to the simulacre of Jean Baudrillard. The changing phases of Korean fashion design are as follows: First, the initial stage involved simple imitation, which replicated the original as much as possible, it expressed the basic composition of Hanbok, flat cut and rich silhouette, the color scheme of traditional colors, traditional patterns, materials, and traditional ornaments. In the second stage, the subject matter intervened to distort and transform from the original, the basic composition and structure of the Hanbok were barely maintained, they were either removed or part of the structure modified or expressed using modern materials and patterns. The third stage, were based on reality but differed from reality through subject and imagination, and only left a part of the basic composition of Hanbok, and were expressed through the partial modification of the elements of the Hanbok, for instance the silhouette, skirt waist, collar and breast-tie. The fourth stage of pure simulacre, which refers to a new image with complete independence regardless of the reality. This stage differed from the basic structure and composition of Hanbok, and showcased traditional Korean image of Korea's unique cultural elements, such as hanbok or crafts and artworks, in a modern fashion with a modern sense and practicality.

• Journal of the Korean Wood Science and Technology
• /
• 제49권5호
• /
• pp.491-503
• /
• 2021

Wood identification is regularly performed by observing the wood anatomy, such as colour, texture, fibre direction, and other characteristics. The manual process, however, could be time consuming, especially when identification work is required at high quantity. Considering this condition, a convolutional neural networks (CNN)-based program is applied to improve the image classification results. The research focuses on the algorithm accuracy and efficiency in dealing with the dataset limitations. For this, it is proposed to do the sample selection process or only take a small portion of the existing image. Still, it can be expected to represent the overall picture to maintain and improve the generalisation capabilities of the CNN method in the classification stages. The experiments yielded an incredible F1 score average up to 93.4% for medium sample area sizes (200 × 200 pixels) on each CNN architecture (VGG16, ResNet50, MobileNet, DenseNet121, and Xception based). Whereas DenseNet121-based architecture was found to be the best architecture in maintaining the generalisation of its model for each sample area size (100, 200, and 300 pixels). The experimental results showed that the proposed algorithm can be an accurate and reliable solution.